Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    see

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens, especially floating-point numbers (i.e. decimal fractions).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     know
    -0.07
    ophobic
    -0.06
    /client
    -0.06
    .innerWidth
    -0.06
    uação
    -0.06
     Hospitality
    -0.06
     fart
    -0.06
    (Register
    -0.06
    (port
    -0.06
     beans
    -0.06
    POSITIVE LOGITS
     Defines
    0.07
     Гар
    0.07
     __('
    0.07
     진
    0.07
     tất
    0.07
     BI
    0.06
     야
    0.06
    613
    0.06
    режд
    0.06
     kilometres
    0.06
    Act Density 0.020%

    No Known Activations